Your question is Imbalanced Data for Anomaly Detection. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
How do you handle imbalanced datasets when training a model for anomaly detection?
Discuss how you would choose between supervised and unsupervised approaches, prevent the majority class from dominating training, select an operating threshold, and evaluate performance when anomalies are rare. Include how you would split the data, validate the model, and monitor it after deployment.
